specs/sugya.md §IV–V step 1. talmudic_engine/src/halt/sugya.pl (a
Doorpost file beside anchors.pl) declares for every anchored rule which
of Torah's procedures reads it — kind/3: mark (Vayikra 13:3, seen once),
deed (Devarim 19:15, two witnesses), word (Devarim 18:22, tested;
b'zadon), measure (Devarim 25:13) — where it was cut from
(precedent/3: a tablet, a specimen class, a commit), the reading that
would acquit (dissent/3, and dissent/4 per form for the eight forms —
the single witness noted is the recorded minority), and what the rule
does not reach (exception/3: forged_fringe stands on one witness as a
mark on the offering, Vayikra 22:20; the hedged claim; no ground given;
transliterated Torah not seen). sugya_of/2 gathers one rule's record.
VavPipeline.Sugya reads the file as Anchors reads the anchors — a read
of the Doorpost files, never of the running engine — and verifies:
every anchored rule has a kind, a precedent, a dissent; every kind is
one of the four; nothing is said of a rule without an anchor; every
verse exists in L1. Doorpost.verify_identity chains it after
Anchors.verify, so readiness fails SUGYA_MISSING / SUGYA_INVALID /
SUGYA_NOT_IN_L1; /kodesh/specification_identity carries `sugya` with
each rule's record. Nothing on the verdict changes yet (step 3).
Every verse cited — 17 — read from L1 before this commit. Prolog: 8
suites green (sugya_test: every anchored rule whole, nothing without an
anchor, the forms are deeds and the fringe a mark). Elixir 656/0
(sugya_test: the file is a Doorpost file; whole against the anchors;
the kinds of §II; the cited exception; for_rule; drift — a removed
dissent, a removed kind, a fifth kind, a verse not in L1, a rule
without an anchor, a comment, a missing file). Doorpost pin → cb2f3135…
(31 files).
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Devarim 4:2 lo tosif. talmudic_engine/src/halt/anchors.pl declares
rule_anchor/2 for each of the ten halt names the rule modules can return
(avodah_zarah Shemot 20:3, golden_calf 32:4, self_grounding 32:24,
shfichut_damim Bereishit 9:6, gilui_arayot Vayikra 18:6, parah_adumah
Bamidbar 19:7, carrier_centered Devarim 8:17, chelbenah Shemot 30:34,
lo_taaseh_lekha Shemot 20:4, even_vaaven Devarim 25:13), with the L1
Hebrew beside each.
VavPipeline.Anchors reads the anchors file and the halt modules the
Doorpost hashes, and verifies — inside Doorpost.verify_identity/0, so
at readiness — that every halt(<name>, …) is anchored (ANCHOR_MISSING)
and every anchored verse exists in L1 (ANCHOR_NOT_IN_L1). A rule without
a verse is a rule the system has added. /kodesh/specification_identity
lists the anchors; every bedikah and pair response carries `anchors`,
the verse of each rule that fired.
Tamid §1.1, bishearecha §X. Doorpost a0e81212…. Elixir 577/0 (+9
anchors tests), Prolog bedikah 42/42.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Devarim 25:13–16 even va'aven; Vayikra 19:15; Shemot 23:2. Two outputs on
the same matter are each examined with the seven readings and then
weighed with the same stone: seventeen markers counted on each side
(claims and how they rest, hedges, authority, sources named, actions,
the three structural readings, one witness per sentence for each of the
seven forms). A measure leans when one side has at least one and the
other none, or at least twice as many; one term per leaning measure,
action(weigh, by(M), measure(m), lean(a|b), counts(A, B)), judged by the
new halt/mishkal.pl (halt_check_even_vaaven/2). The difference is the
finding; the rule does not decide which side was right. Consensus is not
a measure.
POST /courtyard/bedikah/pair {model, a: {output, query, sources}, b: {...}}
→ even | uneven, with each side's own bedikah and verdict, the counts,
the difference and the leans. Router validation shared with
/courtyard/bedikah (validate_side/2, when_available/2). Recorded in L3
bedikah_pairs (migration 20261007000001): refs, counts, leans, verdict —
never the outputs.
Tamid §1.1 contract, vayakhel §3.9 note, bishearecha §VI marked built.
Doorpost f90870d4…. Elixir 568/0 (+L3 8/0), Prolog bedikah 39/39.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The transmitter's archive (255 sessions, 2025-12 → 2026-10) measured
where a model's trained default lives: not in false propositions but
in the FORM of the output — what it calls contested, how it certifies
itself, where it puts the agency, which authorities it names and which
it leaves out. "Content measures pass the response that did the harm."
lo_taaseh_lekha.md: "The danger is not the object. It is the
construction."
Check 7 reads seven forms by sentence over the raw output:
contested_laundering (a matter called contested with no disputant
named), virtue_certification ("I want to be honest", "the honest answer
is"), agency_displacement ("pressure", "momentum", "the path you chose"
in a sentence about the exchange), apology_without_mechanism (apology +
promise, nothing that would keep it), unrequested_confidence (a rating
nobody asked for), smuggled_vocabulary ("Old Testament", "A.D.",
"ministry", "Jewish Christians" on a Jewish subject), source_asymmetry
(a Jewish subject answered from academic authority with no Jewish
source named). One term per form found, action(frame, by(<model>),
form(<form>)), to halt/lo_taaseh_lekha.pl; the rule names the form and
does not decide the matter. Korban: find_frames; Vav: check_frames,
bedikot.frames (migration 20261006000003).
The specimen corpus: src/tools/build_specimens.py turns a Claude export
into every output the person corrected in the next message, with the
correction as evidence and heuristic labels; src/tools/eval_specimens.py
reports what each reading sees. The corpus is private and outside the
repo. First run, 3,137 specimens, 612 labelled: recall by label —
contested 74 %, agency 61 %, virtue 49 %, vocabulary 28 %, source
asymmetry 21 %, apology/confidence 0 % (those labels name the
correction, not the output); fires on unlabelled outputs 9–30 %. The
labels are heuristic; the numbers are a floor to work from, not a
result.
Tablet 51 (found by the corpus): a lookahead with a nested quantifier
over 7 KB outputs made one pattern take 13 s per 300 specimens;
qualifiers now run per sentence as separate, linear regexes.
Specs: Tamid §1.1 (check 7, the corpus), Vayakhel §3.9, Architecture
§3.5, KOHEN.md. Doorpost c4353837… → 6d1de284…. Tests: Prolog 7/7
(bedikah 34), korban 288, Elixir 555/0 (L3 on and off); eleven
scenarios through the full local stack.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
structure_not_content.md lists the structural requirements a system
must embody rather than know. Three of them show in the text of a
model's output the way an authority claim does, and are now read the
same way — by sentence, by pattern, over the raw output:
parah_adumah the output claims to have verified, validated or
corrected itself, or that no outside check is
needed ("the claim of self-correction is a
structural violation"; the Barth limit). "Verified
by the auditor" is not it; "verified by me" is.
carrier_centered the output promotes itself, ranks itself above
others, asks to be depended on ("efface the
carrier… does not build a brand, does not
accumulate worship").
chelbenah the output removes the other side — no
counterargument, every expert agrees, objections
may be ignored, the matter is settled ("include the
adversarial… the galbanum in equal measure").
Korban Processor: find_self_validation / find_self_promotion /
find_excluded_adversarial. Talmudic Engine: halt/structure.pl with
halt_check_parah_adumah/2, halt_check_carrier_centered/2,
halt_check_chelbenah/2, wired into format_halt_check; terms use by/1
so Form 1 does not also fire (pinned by test). Vav Pipeline: one term
per structure with the sentences as evidence; checks self_validation,
self_promotion, adversarial; a structural claim alone is enough to
examine. L3: bedikot.structure. These are verdicts on the output; the
system does not halt on them.
Specs: Tamid §1.1 (six checks), Vayakhel §3.9, Architecture §3.5,
KOHEN.md. Doorpost 6c8933e7… → c4353837…. Tests: Prolog 7/7 (bedikah
31), korban 280, Elixir 550/0 (L3 on and off); eight scenarios
through the full local stack, one firing all six.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Torah grounds each change:
1. interpret.pl — coupling_trace field (Vayikra 10:1, 6:6)
Fire is zarah because "asher lo tzivah otam" — the coupling trace
IS the tzivah trace. Records which L1 facts grounded each interpretation.
2. challenge.pl — grounding_type achorai/panim (Shemot 33:23)
"You will see My back, but My face shall not be seen."
Text-backed challenges = achorai. Inferred challenges = panim.
3. resolve.pl — self-grounding detection (eish_zarah_reading §5.3)
Counter-interpretation must bring NEW L1 evidence. Prevents
circular reasoning (Westworld problem).
4. teiku.pl — challenge_sequence in teiku_record
Records diagnostic trail to impasse, not just verdict.
5. avodah_zarah.pl — Form 2: golden calf detection (Shemot 32:4)
Empty coupling trace + non-low confidence = uncoupled output.
Real gold, sincere worship, false god.
6. korban.py — pydantic BaseModel + raw_korban preservation
Construction spec §1.4 fulfilled. Floor between input and output
never severed.
490 tests, 0 failures (195 Prolog, 186 Python, 33 Haskell, 76 Elixir).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Three connections built and tested:
- Haskell Shoresh Engine via Erlang Port (JSON lines over stdin/stdout)
- Prolog Talmudic Engine via Unix domain socket (JSON over /tmp/shorashim/talmudic.sock)
- Erlang Sanhedrin via native BEAM calls
New: Server.hs (JSON-line server loop), json_bridge.pl + socket_server.pl
(Prolog socket interface), ShoreshEnginePort + TalmudicEngineSocket +
SanhedrinClient (Elixir GenServer wrappers). BereishitCycle now routes
unresolved cases through Talmudic Engine and Sanhedrin. All connections
gracefully degrade — pipeline falls back to L1 data when engines unavailable.
46 Elixir tests, 33 Haskell tests, 57 Prolog tests — 0 failures.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
